Instructions to use jwest33/ministral-3-3b-instruct-2512-null-space-abliterated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jwest33/ministral-3-3b-instruct-2512-null-space-abliterated with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="jwest33/ministral-3-3b-instruct-2512-null-space-abliterated")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("jwest33/ministral-3-3b-instruct-2512-null-space-abliterated")
model = AutoModelForMultimodalLM.from_pretrained("jwest33/ministral-3-3b-instruct-2512-null-space-abliterated")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use jwest33/ministral-3-3b-instruct-2512-null-space-abliterated with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jwest33/ministral-3-3b-instruct-2512-null-space-abliterated"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jwest33/ministral-3-3b-instruct-2512-null-space-abliterated",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/jwest33/ministral-3-3b-instruct-2512-null-space-abliterated

SGLang

How to use jwest33/ministral-3-3b-instruct-2512-null-space-abliterated with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "jwest33/ministral-3-3b-instruct-2512-null-space-abliterated" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jwest33/ministral-3-3b-instruct-2512-null-space-abliterated",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "jwest33/ministral-3-3b-instruct-2512-null-space-abliterated" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jwest33/ministral-3-3b-instruct-2512-null-space-abliterated",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use jwest33/ministral-3-3b-instruct-2512-null-space-abliterated with Docker Model Runner:
```
docker model run hf.co/jwest33/ministral-3-3b-instruct-2512-null-space-abliterated
```

Ministral 3 3B Instruct 2512 - Null-Space Abliterated

mistralai/ministral-3-3b-instruct-2512 with refusal behavior removed via orthogonal projection. Uses null-space constraints and adaptive layer weighting to preserve model capabilities.

Note: This model will produce uncensored outputs. Use responsibly.

GGUF quantizations available at: jwest33/ministral-3-3b-instruct-2512-null-space-abliterated-GGUF

Abliteration Techniques Used

Winsorization: Clips outlier activations at the 99.5th percentile for cleaner refusal direction estimation
Null-Space Projection: Preserves model capabilities by constraining weight updates to the null space of preservation activations
Adaptive Weighting: Applies Gaussian-weighted per-layer ablation strength, focusing on middle-to-later layers where refusal behavior concentrates
Norm Preservation: Maintains original Frobenius norms of weight matrices after projection

Parameter	Value
Harmful Prompts	5000
Harmless Prompts	1226
Winsorization	99.5th percentile
Null-Space Constraints	rank ratio: 0.90
Directional Multiplier	1.10

Credits

Base Model: mistralai/ministral-3-3b-instruct-2512-null-space-abliterated by mistralai
Norm-Preserving Biprojected Abliteration — Jim Lai (grimjim) (2025)
AlphaEdit: Null-Space Constrained Knowledge Editing — Fang et al. (ICLR 2025)
Refusal in Language Models Is Mediated by a Single Direction — Arditi et al. (2024)
Representation Engineering — Zou et al. (2023)

Toolkit Used

github.com/jwest33/abliterator

License

This model inherits the apache-2.0 from the base model. Please review and comply with mistralai's usage terms.

Disclaimer

This model is provided for research and educational purposes. The creators are not responsible for any misuse. Users are solely responsible for ensuring their use complies with applicable laws and ethical standards.

Downloads last month: 8

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for jwest33/ministral-3-3b-instruct-2512-null-space-abliterated

Base model

mistralai/Ministral-3-3B-Base-2512

Quantized

mistralai/Ministral-3-3B-Instruct-2512

Finetuned

(28)

this model

Papers for jwest33/ministral-3-3b-instruct-2512-null-space-abliterated